AI Agent Skills

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failu…

Run GDScript test suites from the command line with `godot --headless`, using a SceneTree/MainLoop runner script that exits non-zero on failure so CI can gate merges. Us…

amWiki 是一款由 JS 开发、依赖 Atom 或 Nodejs-Npm 的 Markdown 轻量级前端化开源文库系统

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expect…

Smart contract security testing and blockchain CTF exploitation. Covers Solidity vulnerability analysis, EVM storage manipulation, delegatecall attacks, CREATE/CREATE2 a…

In-memory SQL engine in Go sql/driver for testing purpose

Writing a Succession-style ensemble series (继承之战群像剧写法) — distilled from Jesse Armstrong's complete shooting scripts for all four seasons, 39 episodes (Faber 2023), with…

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

Scan is a free & Open Source DevSecOps tool for performing static analysis based security testing of your applications and its dependencies. CI and Git friendly.

A sample lab test environment to help in preparation of CKA certification.

a stealthy browser automation framework

Automating Playwright steps using ChatGPT.

Load when building, running, testing, packaging, linting, or configuring a Kotlin/Java project with the Kotlin Toolchain (JetBrains' unified CLI, formerly Amper), when s…

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent chan…

Generate database seed scripts with realistic sample data. Reads Drizzle schemas or SQL migrations, respects foreign key ordering, produces idempotent TypeScript or SQL…

Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client chec…